Skip to main content
Glama

wellpass-mcp

An MCP server to search the EGYM Wellpass fitness network — studios and classes — from any MCP client (Claude Desktop, Claude Code, etc.).

Unofficial. This project is not affiliated with, endorsed by, or supported by EGYM or Wellpass. It talks to Wellpass's own app/web APIs on your behalf, using your own account. Use it for personal use and at your own risk; respect Wellpass's Terms of Service. No warranty (see LICENSE).

Features

Studios (no login required):

  • search_studios — studios near a location, filtered by activities, services, Plus1, studio type, amenities, open-now, radius. City name or lat/lon.

  • get_studio_details — full details for one studio.

  • list_studio_filters — every valid filter value.

Classes (require login — an active Wellpass membership):

  • search_classes — classes for one studio or the online catalogue.

  • search_classes_near — classes across studios near a location, with filters (date, category, teacher, availability, online). Optionally also list nearby studios that offer classes without an in-app schedule.

  • book_class / cancel_booking — two-step (preview, then confirm=true) booking. These WRITE to your account.

Related MCP server: aidoo-mcp-server

Requirements

  • Python 3.11+

  • Optional: uv (faster installs)

Install

git clone <your-fork-url> wellpass-mcp
cd wellpass-mcp
./scripts/setup.sh

The script creates a virtualenv in .venv, installs the package, and creates .env from .env.example.

Manual alternative:

python3 -m venv .venv
.venv/bin/python -m pip install -e ".[dev]"
cp .env.example .env

Configure

Studio search needs no login. For class search/booking, edit .env:

WELLPASS_EMAIL=you@example.com
WELLPASS_PASSWORD=your-password

.env is git-ignored. Credentials are read only from the environment and are never written to any other file.

Register with an MCP client

The server speaks MCP over stdio. Point your client at the venv's Python.

Claude Code:

claude mcp add wellpass -- /absolute/path/to/wellpass-mcp/.venv/bin/python -m wellpass_mcp.server

Claude Desktop (claude_desktop_config.json):

{
  "mcpServers": {
    "wellpass": {
      "command": "/absolute/path/to/wellpass-mcp/.venv/bin/python",
      "args": ["-m", "wellpass_mcp.server"]
    }
  }
}

Then ask your assistant things like:

  • "Find yoga studios within 3 km of Munich with a sauna."

  • "What classes are near me tomorrow morning with free spots?"

  • "Show Fitness First Marienplatz classes on Saturday."

Limitations

  • Classes exist only for some studios. The class API covers studios whose booking is native to the platform (e.g. large chains) plus the online class catalogue. Most small studios use external booking the app only links to; search_classes_near can list them separately but has no times for them.

  • Booking depends on the studio and an active membership. Many classes are check-in based (no reservation). Booking is built but may return an external error for non-reservable classes.

  • The APIs are reverse-engineered and may change without notice.

Development

.venv/bin/python -m pytest -q        # offline tests (from fixtures)
.venv/bin/python -m wellpass_mcp.server   # run the server

See AGENTS.md for architecture and conventions, and docs/api-contract.md for the reverse-engineered API details.

License

MIT — see LICENSE.

Available Tools

7 tools
book_classA

Book the user into a class. TWO-STEP and WRITES to the real account.

Step 1 (confirm=false, default): returns the class details and cancellation window and does NOT book. Relay this to the user. Step 2 (confirm=true): actually books. Only send confirm=true AFTER the user has explicitly agreed to book this specific class.

Args: club_uuid: The class's club_uuid (from a search result). class_id: The class id (from a search result). confirm: Must be true to actually book. Default false (preview only). spot: Optional spot id, for studios with spot selection.

Inputs: class_id (required), club_uuid (required), spot, confirm.

cancel_bookingA

Cancel the user's booking for a class. TWO-STEP and WRITES to the account.

confirm=false (default) previews; confirm=true cancels. Only cancel after the user explicitly agrees. Check the cancellation window first.

Inputs: class_id (required), club_uuid (required), confirm.

get_studio_detailsB

Get full details for one studio by its slug (from search_studios).

Inputs: slug (required).

list_studio_filtersA

List every studio filter value: activities, services, toggles, categories.

This is the ground truth for the activities and services arguments of search_studios. language picks the label language (de/en/fr/nl).

Inputs: region, language.

search_classesA

Search bookable Wellpass classes for a studio (or online), with filters.

Needs WELLPASS_EMAIL and WELLPASS_PASSWORD in .env (classes are gated).

Pick ONE target: - studio_slug: a studio from search_studios (its classes). - club_uuid: the club_uuid field from a search_studios result. - online=True: the online / live-stream class catalogue.

Args: studio_slug: Studio slug whose classes to list. club_uuid: Netpulse club uuid (from search_studios club_uuid). online: Search the online class catalogue instead of a studio. date_from: ISO date/datetime for the window start. Default: now. date_to: ISO date/datetime for the window end. Default: now + 7 days. category: Keep classes whose activity matches (e.g. "yoga", "Body & Mind"). teacher: Keep classes by this instructor (substring, case-insensitive). available_only: Keep only classes with a free spot. limit: Max classes to return (1-100). Default 30.

Returns: A dict with the resolved club, the window, and a class list (soonest first). Each class has name, category, start/end, teacher, free spots, capacity, and online flag.

Inputs: limit, online, date_to, teacher, +5 more.

search_classes_nearA

Find bookable classes NEAR a location, across studios, with filters.

Needs login (.env). Note: only a minority of studios expose structured classes (Netpulse-native, e.g. Fitness First); most small studios use external booking and are not included. Online classes are included by default. The first call near a new area is slower (it probes studios); later calls are fast (native studios are cached).

Args: location: City/place. Default Munich. Ignored if latitude+longitude set. latitude, longitude: Exact search point. radius_km: Only studios within this distance. Default 5 km. date_from, date_to: ISO date/datetime window. Default: now .. now+7d. category: Keep classes whose activity matches (e.g. "yoga", "cardio"). teacher: Keep classes by this instructor (substring, case-insensitive). available_only: Keep only classes with a free spot. include_online: Also include the online class catalogue. Default true. include_studios_without_times: Also list nearby studios that offer classes but expose no in-app schedule (external booking). They come back under studios_without_times, not as timed classes. Default false (hide them). limit: Max classes to return (1-100). Default 40. Soonest first.

Returns: Classes (soonest first), each with studio, distance_km, club_uuid, and a class id — pass club_uuid + id to book_class.

Inputs: limit, date_to, teacher, category, +8 more.

search_studiosA

Search EGYM Wellpass studios (gyms) near a location, with filters.

Args: location: City or place name. Default "Munich". Ignored if latitude and longitude are both given. latitude: Optional exact latitude of the search point. longitude: Optional exact longitude of the search point. radius_km: Only return studios within this distance. Default 10 km. activities: Activity filters. Accept a slug ("activity-yoga"), a bare name ("yoga"), an activity type ("YOGA"), or a label ("Yoga"). Several activities are combined with OR. services: Service/amenity filters, same spelling rules (e.g. "sauna", "service-sauna", "free-parking"). Combined with AND across groups. plus_one: Only studios that allow a Plus1 guest. studio_types: Keep only these studio types (e.g. "PILATES", "WELLNESS"). gym_info: Require these gym-info flags (e.g. "COURSES_IN_ENGLISH", "ACCESSIBLE_TO_PREGNANT_WOMEN"). open_now: Only studios open at the current local time. limit: Max studios to return (1-50). Default 20. region: Catalog: "dach" (default), "all", "us", "fr-be", "dach-us".

Returns: A dict with the resolved center, applied filters, and a ranked studio list (nearest first). Call list_studio_filters for valid filter values.

Inputs: limit, region, gym_info, latitude, +8 more.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4/5.0

    Scored across 7 tools

    Disambiguation4/5

    Most tools have clearly distinct purposes: studio lookup, filter catalog, studio search, class search, booking, and cancellation. The only real overlap is search_classes vs search_classes_near, but the descriptions clearly differentiate per-studio vs location-wide searching.

    Naming Consistency5/5

    All tools follow a consistent snake_case verb_noun pattern (get_*, list_*, search_*, book_*, cancel_*). No mixed conventions or vague verbs.

    Tool Count5/5

    Seven tools is well-scoped for a studio/class discovery and booking domain, with each tool earning its place and no redundancy.

    Completeness4/5

    The surface covers search, detail, filters, class discovery, booking, and cancellation with sensible two-step write semantics. The main gap is the absence of a tool to list the user's existing bookings, which would help before cancelling or rebooking.

    Maintenance

    ActivitySlowing
    ResponsivenessNo recent community issues

    Related MCP Connectors

    • ClassPass MCP server for ChatGPT, Claude and any AI agent: search classes, list reservations, book class, cancel reservation, list class roster, mark attendance, get reservation report and get payout report in your own ClassPass account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to ClassPass yourself; Cotlet does not store your password and you need no ClassPass API key. About the official ClassPass API: ClassPass has an official API, the ClassPass Inventory API, but only approved partners can use it (checked 28 Oct 2026). It lets scheduling software send a studio's schedule, availability and pricing to ClassPass and receive reservations, cancellations and attendance. Setup and FAQ: https://cotlet.dev/integrations/classpass-api-mcp-server

    • Stop manually creating generic reports that don't match your gym! Ask your AI about your studio's sales, classes and clients. Mindbody MCP server for Claude and ChatGPT. Connect your studio once, then ask about sales, classes, clients and memberships. Not affiliated with Mindbody.

      https://studiovector.io/mcp
    • Virtuagym MCP server for ChatGPT, Claude and any AI agent: book member into class, list classes, list members, add lead and add member note in your own Virtuagym account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to Virtuagym yourself; Cotlet does not store your password and you need no Virtuagym API key. About the official Virtuagym API: Virtuagym has an API, but its docs and keys come only by email: "please reach out to api@virtuagym.com and provide us with your Github username" (checked 9 Nov 2026). It has no Zapier app and no official MCP server. Setup and FAQ: https://cotlet.dev/integrations/virtuagym-api-mcp-server

    • Glofox MCP server for ChatGPT, Claude and any AI agent: book member into class, list classes, list members, add lead and check in member in your own Glofox account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to Glofox yourself; Cotlet does not store your password and you need no Glofox API key. About the official Glofox API: Glofox has a REST API for members, memberships, classes, bookings and payments, but the key and token come only on request to ABC Fitness, and its Zapier app needs the Elite plan (checked 8 Nov 2026). It has no official MCP server. Setup and FAQ: https://cotlet.dev/integrations/glofox-api-mcp-server

      https://cotlet.dev/mcp/v1/glofox

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      A universal fitness intelligence layer for AI assistants like Claude, ChatGPT, and Copilot, enabling user profiles, workout/diet plans, calendar scheduling, and gamification via MCP and REST APIs.
      9,324 npm
      MIT
    • A
      license
      B
      quality
      D
      maintenance
      MCP server for Aidoo fitness studio management software, enabling access to members, contracts, classes, bookings, and more directly from Claude.
      25
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables interaction with simulated fitness data (activity history, wellness, pain logging, coaching rules) via MCP protocol, allowing Claude Desktop to query and log data through natural language.
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables ChatGPT to manage fitness routines, guided sessions, workout history, body weight tracking, and statistics through a remote authenticated MCP server with read and write tools.
      AGPL 3.0